<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
  </head>
  <body dir="ltr">
    <br>
    <div class="moz-forward-container">
      <div class="moz-forward-container">
        <div class="moz-forward-container">
          <div class="moz-forward-container">
            <div class="moz-forward-container">
              <style type="text/css" style="display:none;">P {margin-top:0;margin-bottom:0;}</style>
              <div style="font-family: Tahoma, Geneva, sans-serif;
                font-size: 10pt; color: rgb(0, 0, 0);"> Colleagues,</div>
              <div style="font-family: Tahoma, Geneva, sans-serif;
                font-size: 10pt; color: rgb(0, 0, 0);"> <br>
              </div>
              <div style="font-family: Tahoma, Geneva, sans-serif;
                font-size: 10pt; color: rgb(0, 0, 0);">  As
                Editor-in-Chief of Decision Analysis, I am delighted to
                announce that one of the finalists for the
                Clemen-Kleinmuntz Decision Analysis Best Paper Award
                from the journal for 2022 is Dr. Eric Bickel of the
                Department of Operations Research and Industrial
                Engineering at UT Austin, for the following paper: <br>
                <br>
                <div style="font-family: Tahoma, Geneva, sans-serif;
                  font-size: 10pt; color: rgb(0, 0, 0);
                  background-color: rgb(255, 255, 255);" class="elementToProof ContentPasted0 ContentPasted1
                  ContentPasted2 ContentPasted3 ContentPasted4
                  ContentPasted5">
                  Colin Small, J. Eric Bickel <br class="ContentPasted5">
                  <strong><a class="pop ContentPasted5" href="https://pubsonline.informs.org/stoken/default+domain/PR-2-2023/full/10.1287/deca.2022.0457" data-loopstyle="link">Model Complexity and
                      Accuracy: A COVID-19 Case Study</a></strong><br>
                </div>
                <a href="https://pubsonline.informs.org/stoken/default+domain/PR-2-2023/full/10.1287/deca.2022.0457" id="LPlnk763433" class="moz-txt-link-freetext">https://pubsonline.informs.org/stoken/default+domain/PR-2-2023/full/10.1287/deca.2022.0457</a><a class="moz-txt-link-freetext" href="https://doi.org/10.1287/deca.2020.0421" moz-do-not-send="true"></a><br>
                <br>
                When creating mathematical models for forecasting and
                decision making, there is a tendency to include more
                complexity than necessary, in the belief that
                higher-fidelity models are more accurate than simpler
                ones. In this paper, we analyze the performance of
                models that submitted COVID-19 forecasts to the U.S.
                Centers for Disease Control and Prevention and evaluate
                them against a simple two-equation model that is
                specified using simple linear regression. We find that
                our simple model was comparable in accuracy to highly
                publicized models and had among the best-calibrated
                forecasts.This result may be surprising given the
                complexity of many COVID-19 models and their support by
                large forecasting teams. However, our result is
                consistent with the body of research that suggests that
                simple models perform very well in a variety of
                settings.<br>
              </div>
            </div>
          </div>
        </div>
      </div>
    </div>
  </body>
</html>